Short dataset description

Three datasets are used:

  1. Players contains 3922 observations of 7 variables.

  2. player_data contains 4550 observations of 8 variables.

  3. Seasons_Stats contains 24691 observations of 53 variables.

General Statistics

Points per game

Ppg <- Seasons_stats %>%
  group_by(Player)%>%
  summarise(sum.PTS = sum(PTS), sum.G = sum(G))%>%
  mutate(avg.PTSperG = sum.PTS/sum.G) %>%
  #ungroup()%>%
  select(Player,sum.PTS, sum.G,avg.PTSperG)%>%
  arrange(desc(avg.PTSperG))
## `summarise()` ungrouping output (override with `.groups` argument)
p <- ggplot(Ppg, aes (
        x = sum.G, 
        y = avg.PTSperG,
        color = Player,
        shape = ifelse(Player == 'Michael Jordan*', 'TRUE', 'FALSE')
        #size = avg.PTSperG
        )) +
        geom_point(aes (alpha = 1 / 10)) +
        scale_shape_manual(guide = F, values = c(18,15))+
        theme(legend.position = "none")

fig <- ggplotly(p)
fig